Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SetTitle
    -0.07
    updates
    -0.06
     Ches
    -0.06
    ける
    -0.06
     swap
    -0.06
    Gb
    -0.06
    bai
    -0.06
    Dep
    -0.06
     Những
    -0.06
    Any
    -0.06
    POSITIVE LOGITS
     ├──
    0.07
    _CLIENT
    0.07
     تنظيف
    0.07
     beaut
    0.07
     hazardous
    0.06
    belongs
    0.06
    ö
    0.06
    ΟΚ
    0.06
    leine
    0.06
    amacare
    0.06
    Act Density 0.013%

    No Known Activations